All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,972
- 666
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 10,657–10,680 of 15,972 skills
- Role Tech LeadTech Lead role in AID methodology. Use for architecture decisions, code reviews, technical direction, operational readiness, team guidance.Votes: 0GitHub stars: 9
- Role DeveloperDeveloper role in AID methodology. Use for implementation, debugging, technical design, TDD workflow, code review.Votes: 0GitHub stars: 9
- ReflectionAutomatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation without conversation context bias.Votes: 0GitHub stars: 9
- Tech Lead> **Source**: `../role-tech-lead/SKILL.md` > > This file is a reference. The main skill definition is in the `.claude/skills/` directory.Votes: 0GitHub stars: 9
- Development> **Source**: `../aid-development/SKILL.md` > > This file is a reference. The main skill definition is in the `.claude/skills/` directory.Votes: 0GitHub stars: 9
- Breakdown> **Source**: `../../commands/jira-breakdown.md` > > This file is a reference. The main prompt is in the `../../commands/` directory. > Use the `/jira-breakdown` command for work breakdown generation.Votes: 0GitHub stars: 9
- Unigrpo Unified Visual Generation RlReplace classifier-free guidance and KL-based regularization in flow matching with velocity-based MSE regularization and GRPO for joint text-image optimization. Achieves 0.8381 TextAlign and 0.90 GenEval without CFG overhead. Works best for multimodal generation where text and image must stay coherent. Trigger: When optimizing vision-language models with flow matching and need better joint text-image policy.Votes: 0GitHub stars: 6
- Generalized Discrete Diffusion SnapshotsUnify discrete diffusion for language by replacing token-wise uniform masking with generalized noising via rate matrices and snapshot latents, enabling semantic-aware forward processes. Demonstrates 1.16 BPC on Text8 and 7.65 perplexity on OpenWebText, beating autoregressive baselines; enables generalized noising processes over arbitrary vocabularies with efficient training aligned to standard architectures.Votes: 0GitHub stars: 6
- F4splat Feed Forward DensificationEnable spatially adaptive Gaussian allocation in 3D Gaussian Splatting without iterative optimization. Reduces primitive count by 70-90% while maintaining reconstruction quality through learned densification score prediction.Votes: 0GitHub stars: 6
- Yolo Moe DetectionMoE-enhanced YOLOv9-Tiny using lightweight routers to adaptively weight specialized expert outputs at each feature resolution, improving detection quality while maintaining end-to-end differentiability. Deploy for efficient multi-scale object detection with dynamic specialization.Votes: 0GitHub stars: 6
- Web Agent Declarative FrameworkEnable safe and efficient AI agent interactions with websites via declarative HTML extensions—define agent-executable tools and context using <tool> and <context> tags instead of relying on brittle UI inference.Votes: 0GitHub stars: 6
- Vmoba Sparse Video AttentionReduces video diffusion training compute 2.92× through spatio-temporal sparse attention with layer-wise cyclic block partitioning. Maintains generation quality while enabling long-sequence video training. Use when training video models on memory-constrained hardware or processing longer video sequences.Votes: 0GitHub stars: 6
- Videossm Long VideoGenerate minute-scale coherent videos using state-space models as evolving memory for scene dynamics. VideoSSM achieves linear computational complexity while reducing motion drift—ideal when temporal consistency matters across long video sequences.Votes: 0GitHub stars: 6
- Verifier Free Test Time SamplingUse model confidence and prediction consistency to select high-quality actions at test time without external verifiers, enabling reliable action selection in VLA systems.Votes: 0GitHub stars: 6
- V Thinker Interactive Visual ReasoningEnable vision-centric interactive reasoning by synthesizing diverse reasoning datasets through co-evolutionary loops, then training models with progressive curriculum that starts with perception and advances to tool-based problem solving.Votes: 0GitHub stars: 6
- Think Right Reasoning Allocation CalibrationDynamically allocate reasoning budgets per-task: 36.8% length reduction while improving accuracy 8.4% by learning which problems warrant deep reasoning vs. quick answers. Use when optimizing reasoning efficiency across variable-difficulty problems.Votes: 0GitHub stars: 6
- Swimbird Switchable ReasoningEnable multimodal models to dynamically switch between text and vision reasoning modes, allocating computation based on perceived difficulty and image resolution, achieving strong performance on both vision-dense and text-heavy benchmarks.Votes: 0GitHub stars: 6
- Swe Universe EnvironmentsAutomatically generate executable software engineering environments from GitHub pull requests at million-scale using an autonomous building agent. Detects superficial verification patterns to force genuine code execution testing.Votes: 0GitHub stars: 6
- Swe Debate Multi Agent Issue ResolutionFramework orchestrating competitive debate among specialized agents with different reasoning perspectives. Generates multiple fault propagation traces via code dependency graphs, then resolves to consolidated fixes through structured multi-round competition.Votes: 0GitHub stars: 6
- Streaming Video GenerationGenerate videos in real-time (16 FPS) by streaming frames continuously via modified flow matching with moving buffer mechanism and adaptive time embeddings.Votes: 0GitHub stars: 6
- Stepsize Learning RateImprove training efficiency under iteration budgets using the Unified Budget-Aware (UBA) schedule, a theoretically grounded learning rate approach governed by a single hyperparameter φ that balances adaptability across network architectures.Votes: 0GitHub stars: 6
- Stagevar AccelerationAccelerate visual autoregressive (VAR) image generation 3.4× without retraining by analyzing generation stages. Exploits semantic irrelevance in detail-refinement stages where classifier-free guidance becomes redundant and features exhibit low-rank structure—enabling dimensionality reduction while preserving output quality.Votes: 0GitHub stars: 6
- Srpo Vla PolicyTrain VLA models for robotic manipulation by using the model's own successful trajectories as self-reference for reward—enable progress-based feedback for failed attempts without external rewards or demonstrations.Votes: 0GitHub stars: 6
- Sonicmoe Training OptimizationOptimize MoE training through memory-efficient backward pass, IO-aware kernel design overlapping memory operations, and token rounding routing. Avoid caching large-scale activations, fuse operations with GEMM, implement ping-pong scheduling. Achieve 1.86× compute throughput on Hopper GPUs and 16% higher TFLOPS in sparse configurations.Votes: 0GitHub stars: 6